Llama Guard models

4 Llama Guard models from Meta on Hugging Face, from 1.2B to 12.0B parameters, published by Meta in BF16, with a 10M-token context. The smallest official model, Llama-Guard-3-1B, needs about 3.3 GB of VRAM at its published precision; the cheapest live fit is RTX 3070 at $0.088/hr.

Part of the Llama series

Pick a size

One row per official Llama Guard size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.

ModelParametersNative VRAMFP8 VRAMINT4 VRAMLive GPU fit (native)Est. $/hrKV cache at 32K
Llama-Guard-3-1B1.5B3.3 GB1.7 GB0.8 GBRTX 3070$0.088/hrnot published for this architecture
Llama-Guard-3-8B8.0B17.9 GB9.0 GB4.5 GBRTX A5000$0.176/hrnot published for this architecture
Llama-Guard-4-12B12.0B26.8 GB13.4 GB6.7 GBRTX A6000$0.363/hr6.0 GB

VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.

Official models (3)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
Llama-Guard-3-1B1.5BBF163.3 GBRTX 3070$0.088/hr
Llama-Guard-3-8B8.0BBF1617.9 GBRTX A5000$0.176/hr
Llama-Guard-4-12B12.0BBF1626.8 GBRTX A6000$0.363/hr

Fine-tunes and community models (1)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
Llama-Phishsense-1B1.2BBF162.8 GBRTX 3070$0.088/hr

VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.

More from Meta

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.